INDEX

Explanations

information related to a specific location or setting, focusing on descriptions of physical attributes and historical background

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ordina

-1.17

 wien

-1.17

 milano

-1.17

 kombi

-1.16

 utop

-1.13

 bayern

-1.12

 frankfurt

-1.11

 incess

-1.11

hek

-1.10

 banan

-1.09

POSITIVE LOGITS

 original

0.67

 preserved

0.67

original

0.60

 donated

0.59

 recovered

0.58

 museum

0.56

 restored

0.55

 memorabilia

0.55

Original

0.55

 originals

0.55

Activations Density 0.559%

information related to a specific location or setting, focusing on descriptions of physical attributes and historical background

No Comments

No Known Activations